Evaluation of Header Field Entropy for Hash-Based Packet Selection

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4979)


Network Measurements play an essential role in operating and developing today’s Internet. High data rates and complex measurement demands can origin an immense resource consumption for measurement tasks. Data selection techniques, like sampling and filtering, provide efficient solutions for reducing resource consumption while still maintaining sufficient information about the metrics of interest. Hash-based packet selection allows a synchronized selection of packets at multiple observation points. With this, the tracking of the path of a packet and the calculation of multipoint QoS metrics like one-way delay becomes possible. Nevertheless, hash-based selection is deterministic based on parts of the packet content and hence it is suspect to bias. The packet content used for hashing is a source for bias if the selected content is not variable enough. This paper empirically analyzes which header bytes are most variable and recommendable as input for hash-based selection if one targets the emulation of random selection.


Hash Function High Entropy Destination Address Input Length Trace Group 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Niccolini, S., Molina, et al.: Design and implementation of a one way delay passive measurement system. In: Network Operations and Management Symposium (2004)Google Scholar
  2. 2.
    Zseby, T., Zander, S., Carle, G.: Evaluation of building blocks for passive one-way-delay measurements. In: PAM Workshop, Amsterdam, Netherlands (April 2001)Google Scholar
  3. 3.
    Duffield, N., Grossglauser, M.: Trajectory sampling for direct traffic observation. IEEE/ACM Trans. Netw. 9(3), 280–292 (2001)CrossRefGoogle Scholar
  4. 4.
    Snoeren, A., Partridge, C., et al.: Single-packet ip traceback. IEEE/ACM Trans. Netw. 10(6), 721–734 (2002)CrossRefGoogle Scholar
  5. 5.
    Active measurement project,
  6. 6.
  7. 7.
    Papagiannaki, K., Moon, S., et al.: Analysis of measured single-hop delay from an operational back bone network. IEEE Infocom, New York (June 2002)Google Scholar
  8. 8.
    Choi, B.Y., Moon, S., et al.: Practical delay monitoring for ISPs. In: ACM Conference on Emerging network experiment and technology. ACM Press, New York (2005)Google Scholar
  9. 9.
    Henke, C., Schmoll, C., Zseby, T.: Empirical evaluation of hash functions for multipoint measurements. Technical Report TR-2007-11-01 (Available upon request)Google Scholar
  10. 10.
    Molina, M., Niccolini, S., Duffield, N.G.: Comparative experimental study of hash functions applied to packet sampling. In: ITC-19 (August 2005)Google Scholar
  11. 11.
    Jian, G., Guang, C.: Distributed sampling measurement model in a large-scale high-speed ip networks. Journal of Southeast University, Nanjing, China (2002)Google Scholar
  12. 12.
    Zseby, T., Molina, M., et al.: Sampling and filtering techniques for IP packet selection. In: IETF Internet Draft (2007)Google Scholar
  13. 13.
    Bronstein, I.N.: Taschenbuch der Mathematik Teubner, Leipzig (1962)Google Scholar
  14. 14.
    Traffic measurement database MOME,

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  1. 1.Fraunhofer Institute FokusBerlinGermany

Personalised recommendations